Client overview

The university is a global leader in higher education offering a wide variety of learning paths and degrees. The university has proven to be a forward-thinking institution that has successfully embraced AI-driven technologies to address key challenges and achieve remarkable results.

Smarter student identification and performance monitoring through automated administration

The university sought an effective solution that would not only identify prospective students with a high chance of registration but also provide insights on student persistence and enrolment for each course before every semester. The ultimate aim was to boost student enrolment across faculties, improve student retention rates and maximize the efficiency of administration. Additionally, they aimed to reduce labor costs by automating and streamlining these processes.

Qualitest, in collaboration with the AI SVP and key stakeholders from the university, developed, tested and rolled out three predictive models were developed to address the identified challenges.

Three AI solutions for simpler, speedier university administration processes

The models, namely the Leads Conversion model, the Student Retention model, and the Class Registration model, were designed to leverage data and provide valuable predictions to improve student enrolment rates, prediction of course registrants and student retention.

Leads Conversion Model

The Leads Conversion model, which won a prestigious national award in 2021, serves as an active solution that runs every semester. Its primary purpose is to prioritize potential leads for registration. By analyzing various data points, the Leads Conversion model identifies interested parties with a high chance of enrolling at the university. At the same time, the model also successfully filters out many leads who are interested but will not register. This lead prioritization operation enables the university to focus its efforts and resources on prospects who are most likely to convert, optimizing enrollment rates and streamlining the admissions process.

Student Retention Model

The Student Retention model aims to provide a forecast on student degree completion. By leveraging predictive analytics, the model generates insights and visually represents them through a dedicated operational system. This intuitive representation informs the ‘persistence unit’ about the likelihood of individual students completing their degree. It enables early intervention and targeted support to improve student retention rates and ensure a higher rate of successful degree completions. It also prevents unnecessary intervention with students with very high potential to graduate.

Class Registration Model

The Registration model focuses on predicting the number of students expected to enroll in each course before every semester. By analyzing historical data and incorporating factors such as student performance in courses, course popularity, and other factors, the model provides accurate enrolment forecasts. As the current course enrolment predictions are made ad hock and often miss the actual enrolments, this valuable information enables the university to make data-driven decisions regarding course offerings, resource allocation, and scheduling, optimizing student experiences and maximizing course fill rates.

Key benefits

The predictive model’s ability to effectively identify and prioritize prospective students with a high likelihood of registration has undoubtedly contributed to the institution’s growth and success.

By implementing predictive models, the university was able to:

  • Improve conversion rate of leads to students by 97% by correctly identifying 80% of leads that have registered for studies, and correctly filtering out 75% of leads that did not register to studies.
  • Cut down labor costs for call center employees at a time when it was facing the challenge of a growing number of leads in each semester.
  • Demonstrate to stakeholders and market the university brand as a pioneer in the education sector that embraces AI-driven technologies.
  • Provide the university with a strong foundation in data science driven decision-making, future-proofing the university to navigate the evolving education landscape.
  • Further enhance their competitiveness and solidify their reputation as a leading academic institution.

Overall, the implementation and future development of these predictive models hold great potential to enhance the university’s competitiveness, student retention, and operational efficiency. Their innovative approach to student recruitment, retention, and resource allocation showcases their commitment to delivering a superior educational experience.

New call-to-action Download the PDF